Michunie's picture
First training
70182bb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9840872883796692,
"min": 0.9840872883796692,
"max": 2.8611769676208496,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9396.0654296875,
"min": 9396.0654296875,
"max": 29301.3125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.798335075378418,
"min": 0.39565780758857727,
"max": 12.798335075378418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2495.67529296875,
"min": 76.75761413574219,
"max": 2601.67236328125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06954128075220996,
"min": 0.06447596270408408,
"max": 0.07194801254509538,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27816512300883983,
"min": 0.2653735689602007,
"max": 0.3597400627254769,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1955335041617646,
"min": 0.12243298709839948,
"max": 0.279927460936939,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7821340166470584,
"min": 0.4897319483935979,
"max": 1.399637304684695,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.295454545454547,
"min": 3.7045454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 163.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.7045454545454546,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 163.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674387384",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674387813"
},
"total": 429.40435683399994,
"count": 1,
"self": 0.39069199999983084,
"children": {
"run_training.setup": {
"total": 0.10892397800000708,
"count": 1,
"self": 0.10892397800000708
},
"TrainerController.start_learning": {
"total": 428.9047408560001,
"count": 1,
"self": 0.5193509779928718,
"children": {
"TrainerController._reset_env": {
"total": 8.87943253200001,
"count": 1,
"self": 8.87943253200001
},
"TrainerController.advance": {
"total": 419.38381734500706,
"count": 18203,
"self": 0.271110227009558,
"children": {
"env_step": {
"total": 419.1127071179975,
"count": 18203,
"self": 273.0501425870169,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.79899419297897,
"count": 18203,
"self": 1.413562755954672,
"children": {
"TorchPolicy.evaluate": {
"total": 144.3854314370243,
"count": 18203,
"self": 31.84654099904367,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.53889043798063,
"count": 18203,
"self": 112.53889043798063
}
}
}
}
},
"workers": {
"total": 0.2635703380016139,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.6664742549941,
"count": 18203,
"is_parallel": true,
"self": 207.06266314299558,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00805953999997655,
"count": 1,
"is_parallel": true,
"self": 0.004054720999874917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004004819000101634,
"count": 10,
"is_parallel": true,
"self": 0.004004819000101634
}
}
},
"UnityEnvironment.step": {
"total": 0.03400678399998469,
"count": 1,
"is_parallel": true,
"self": 0.0004489020000164601,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031197800001336873,
"count": 1,
"is_parallel": true,
"self": 0.00031197800001336873
},
"communicator.exchange": {
"total": 0.031395963000022675,
"count": 1,
"is_parallel": true,
"self": 0.031395963000022675
},
"steps_from_proto": {
"total": 0.001849940999932187,
"count": 1,
"is_parallel": true,
"self": 0.0004414480000605181,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014084929998716689,
"count": 10,
"is_parallel": true,
"self": 0.0014084929998716689
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.60381111199854,
"count": 18202,
"is_parallel": true,
"self": 8.285995232994196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.054006829993227,
"count": 18202,
"is_parallel": true,
"self": 5.054006829993227
},
"communicator.exchange": {
"total": 176.7112925440033,
"count": 18202,
"is_parallel": true,
"self": 176.7112925440033
},
"steps_from_proto": {
"total": 30.552516505007816,
"count": 18202,
"is_parallel": true,
"self": 6.545774075024383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.006742429983433,
"count": 182020,
"is_parallel": true,
"self": 24.006742429983433
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.027800014227978e-05,
"count": 1,
"self": 4.027800014227978e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 416.4227124239334,
"count": 342204,
"is_parallel": true,
"self": 9.090499234921936,
"children": {
"process_trajectory": {
"total": 240.05112936001092,
"count": 342204,
"is_parallel": true,
"self": 239.28776997301088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7633593870000368,
"count": 4,
"is_parallel": true,
"self": 0.7633593870000368
}
}
},
"_update_policy": {
"total": 167.28108382900052,
"count": 90,
"is_parallel": true,
"self": 40.16272421300687,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.11835961599365,
"count": 4587,
"is_parallel": true,
"self": 127.11835961599365
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12209972300001937,
"count": 1,
"self": 0.0010151150002002396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12108460799981913,
"count": 1,
"self": 0.12108460799981913
}
}
}
}
}
}
}